Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1097. Min Range: -6.1097
Max Act: 6.1097. Min Act: -0.1700
Data Index: 255790 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1097. Min Range: -6.1097
Max Act: 6.0472. Min Act: -0.1700
Data Index: 8676121 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.9847. Min Act: -0.1700
Data Index: 2832289 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.9535. Min Act: -0.1700
Data Index: 8467341 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.9222. Min Act: -0.1700
Data Index: 4125530 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.8910. Min Act: -0.1700
Data Index: 8654500 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.8910. Min Act: -0.1700
Data Index: 2485821 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.8597. Min Act: -0.1700
Data Index: 7106914 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.8285. Min Act: -0.1700
Data Index: 189059 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6910634 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 2857179 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 211504 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 1431273 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 4160100 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 4567851 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6198992 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7660. Min Act: -0.1700
Data Index: 5398179 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7660. Min Act: -0.1700
Data Index: 839124 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7660. Min Act: -0.1700
Data Index: 4296995 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1097. Min Range: -6.1097
Max Act: 5.7347. Min Act: -0.1700
Data Index: 97875 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19